DIT-Comunicaciones a Congresos, Conferencias...
URI permanente para esta colecciónhttps://hdl.handle.net/10953/228
Examinar
Examinando DIT-Comunicaciones a Congresos, Conferencias... por Autor "Martínez-Colón, Antonio"
Mostrando 1 - 2 de 2
- Resultados por página
- Opciones de ordenación
Ítem Attentional Mechanism Based on a Microphone Array for Embedded Devices and a Single Camera(Springer, 2018-11-21) Martínez-Colón, Antonio; Pérez-Lorenzo, José Manuel; Rivas, Fernando; Viciana-Abad, Raquel; Reche-López, PedroThis work presents an attentional mechanism with the capability of detecting the localization of a speaker for interaction purposes, based on audio and video information. The localization is computed in terms of azimuth and elevation angles, to be used as input values for controlling mobile systems such as a pan-tilt videocamera or a robotic head. For this purpose the SRP-PHAT algorithm has been implemented with a commercial array of microphones for embedded devices, in order to estimate the localization of a sound source in the surroundings of the array. In order to improve the limitations of the SRP-PHAT algorithm in the estimation of the z coordinate, the elevation angle is corrected via video information by using Haar cascade classifiers for face detection. Simulations and experiments show the accuracy of the system, as well as the application for controlling a pan-tilt videocamera in a real scenario with speakers and ambient noise.Ítem Evaluation of a Multi-speaker System for Socially Assistive HRI in Real Scenarios(Springer, 2020-11-03) Martínez-Colón, Antonio; Viciana-Abad, Raquel; Pérez-Lorenzo, José Manuel; Evers, Christine; Naylor, Patrick A.In the field of social human-robot interaction, and in particular for social assistive robotics, the capacity of recognizing the speaker’s discourse in very diverse conditions and where more than one interlocutor may be present, plays an essential role. The use of a mics. array that can be mounted in a robot supported by a voice enhancement module has been evaluated, with the goal of improving the performance of current automatic speech recognition (ASR) systems in multi-speaker conditions. An evaluation has been made of the improvement in terms of intelligibility scores that can be achieved in the operation of two off-the-shelf ASR solutions in situations that contemplate the typical scenarios where a robot with these characteristics can be found. The results have identified the conditions in which a low computational cost demand algorithm can be beneficial to improve intelligibility scores in real environments.